© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 102887
    Prev
    Next
    INDEX
    Explanations

    Inside

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -br
    -0.08
     luckily
    -0.07
     zawsze
    -0.07
    Poor
    -0.07
    These
    -0.07
     thấp
    -0.07
    Usually
    -0.07
     fortunately
    -0.07
     لأنها
    -0.07
     всегда
    -0.07
    POSITIVE LOGITS
     Inside
    0.13
     wherein
    0.12
    Inside
    0.11
     Dentro
    0.11
     inside
    0.11
     wobei
    0.11
    Dentro
    0.10
    _inside
    0.10
     corresponding
    0.10
     Где
    0.10
    Activations Density 0.013%

    No Known Activations